© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115755
    Prev
    Next
    INDEX
    Explanations

    version. version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    റ്
    -0.77
    ссию
    -0.74
    GAT
    -0.72
     benö
    -0.69
     вне
    -0.69
    util
    -0.68
    」。
    -0.68
    риса
    -0.67
    医生
    -0.67
    varphi
    -0.67
    POSITIVE LOGITS
    SDK
    1.01
    sdk
    0.99
     Legion
    0.94
     SDK
    0.84
    coden
    0.82
    гости
    0.82
     sdk
    0.81
     ము
    0.80
     decode
    0.79
    REFERENCES
    0.78
    Activations Density 0.009%

    No Known Activations